{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Welcome to the start of your adventure in Agentic AI" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", " \n", " \n", " \n", " \n", "
\n", " \n", " \n", "

Are you ready for action??

\n", " Have you completed all the setup steps in the setup folder?
\n", " Have you read the README? Many common questions are answered here!
\n", " Have you checked out the guides in the guides folder?
\n", " Well in that case, you're ready!!\n", " \n", "
" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", " \n", " \n", " \n", " \n", "
\n", " \n", " \n", "

This code is a live resource - keep an eye out for my updates

\n", " I push updates regularly. As people ask questions or have problems, I add more examples and improve explanations. As a result, the code below might not be identical to the videos, as I've added more steps and better comments. Consider this like an interactive book that accompanies the lectures.

\n", " I try to send emails regularly with important updates related to the course. You can find this in the 'Announcements' section of Udemy in the left sidebar. You can also choose to receive my emails via your Notification Settings in Udemy. I'm respectful of your inbox and always try to add value with my emails!\n", " \n", "
" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### And please do remember to contact me if I can help\n", "\n", "And I love to connect: https://www.linkedin.com/in/eddonner/\n", "\n", "\n", "### New to Notebooks like this one? Head over to the guides folder!\n", "\n", "Just to check you've already added the Python and Jupyter extensions to Cursor, if not already installed:\n", "- Open extensions (View >> extensions)\n", "- Search for python, and when the results show, click on the ms-python one, and Install it if not already installed\n", "- Search for jupyter, and when the results show, click on the Microsoft one, and Install it if not already installed \n", "Then View >> Explorer to bring back the File Explorer.\n", "\n", "And then:\n", "1. Click where it says \"Select Kernel\" near the top right, and select the option called `.venv (Python 3.12.9)` or similar, which should be the first choice or the most prominent choice. You may need to choose \"Python Environments\" first.\n", "2. Click in each \"cell\" below, starting with the cell immediately below this text, and press Shift+Enter to run\n", "3. Enjoy!\n", "\n", "After you click \"Select Kernel\", if there is no option like `.venv (Python 3.12.9)` then please do the following: \n", "1. On Mac: From the Cursor menu, choose Settings >> VS Code Settings (NOTE: be sure to select `VSCode Settings` not `Cursor Settings`); \n", "On Windows PC: From the File menu, choose Preferences >> VS Code Settings(NOTE: be sure to select `VSCode Settings` not `Cursor Settings`) \n", "2. In the Settings search bar, type \"venv\" \n", "3. In the field \"Path to folder with a list of Virtual Environments\" put the path to the project root, like C:\\Users\\username\\projects\\agents (on a Windows PC) or /Users/username/projects/agents (on Mac or Linux). \n", "And then try again.\n", "\n", "Having problems with missing Python versions in that list? Have you ever used Anaconda before? It might be interferring. Quit Cursor, bring up a new command line, and make sure that your Anaconda environment is deactivated: \n", "`conda deactivate` \n", "And if you still have any problems with conda and python versions, it's possible that you will need to run this too: \n", "`conda config --set auto_activate_base false` \n", "and then from within the Agents directory, you should be able to run `uv python list` and see the Python 3.12 version." ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": [ "# First let's do an import. If you get an Import Error, double check that your Kernel is correct..\n", "\n", "from dotenv import load_dotenv\n" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "True" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Next it's time to load the API keys into environment variables\n", "# If this returns false, see the next cell!\n", "\n", "load_dotenv(override=True)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Wait, did that just output `False`??\n", "\n", "If so, the most common reason is that you didn't save your `.env` file after adding the key! Be sure to have saved.\n", "\n", "Also, make sure the `.env` file is named precisely `.env` and is in the project root directory (`agents`)\n", "\n", "By the way, your `.env` file should have a stop symbol next to it in Cursor on the left, and that's actually a good thing: that's Cursor saying to you, \"hey, I realize this is a file filled with secret information, and I'm not going to send it to an external AI to suggest changes, because your keys should not be shown to anyone else.\"" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", " \n", " \n", " \n", " \n", "
\n", " \n", " \n", "

Final reminders

\n", " 1. If you're not confident about Environment Variables or Web Endpoints / APIs, please read Topics 3 and 5 in this technical foundations guide.
\n", " 2. If you want to use AIs other than OpenAI, like Gemini, DeepSeek or Ollama (free), please see the first section in this AI APIs guide.
\n", " 3. If you ever get a Name Error in Python, you can always fix it immediately; see the last section of this Python Foundations guide and follow both tutorials and exercises.
\n", " \n", "
" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "OpenAI API Key exists and begins AKIAUWQI\n" ] } ], "source": [ "# Check the key - if you're not using OpenAI, check whichever key you're using! Ollama doesn't need a key.\n", "\n", "import os\n", "openai_api_key = os.getenv('AWS_ACCESS_KEY_ID')\n", "\n", "if openai_api_key:\n", " print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n", "else:\n", " print(\"OpenAI API Key not set - please head to the troubleshooting guide in the setup folder\")\n", " \n" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [], "source": [ "# And now - the all important import statement\n", "# If you get an import error - head over to troubleshooting in the Setup folder\n", "# Even for other LLM providers like Gemini, you still use this OpenAI import - see Guide 9 for why\n", "\n", "from openai import OpenAI" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [], "source": [ "# And now we'll create an instance of the OpenAI class\n", "# If you're not sure what it means to create an instance of a class - head over to the guides folder (guide 6)!\n", "# If you get a NameError - head over to the guides folder (guide 6)to learn about NameErrors - always instantly fixable\n", "# If you're not using OpenAI, you just need to slightly modify this - precise instructions are in the AI APIs guide (guide 9)\n", "\n", "openai = OpenAI(\n", " # VERY IMPORTANT! This redirects OpenAI commands to the Amazon Bedrock servers\n", " base_url=\"https://bedrock-runtime.ap-south-1.amazonaws.com/openai/v1\", \n", " # In Bedrock's compatibility mode, the API key is just your AWS Secret\n", " api_key=os.getenv('AWS_SECRET_ACCESS_KEY')\n", ")" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [], "source": [ "# Create a list of messages in the familiar OpenAI format\n", "\n", "messages = [{\"role\": \"user\", \"content\": \"What is 2+2?\"}]" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "ename": "AuthenticationError", "evalue": "Error code: 401 - {'error': {'message': 'Invalid API Key format: Must start with pre-defined prefix', 'type': 'permission_denied_error', 'param': None, 'code': 'access_denied'}}", "output_type": "error", "traceback": [ "\u001b[31m---------------------------------------------------------------------------\u001b[39m", "\u001b[31mAuthenticationError\u001b[39m Traceback (most recent call last)", "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[14]\u001b[39m\u001b[32m, line 6\u001b[39m\n\u001b[32m 1\u001b[39m \u001b[38;5;66;03m# And now call it! Any problems, head to the troubleshooting guide\u001b[39;00m\n\u001b[32m 2\u001b[39m \u001b[38;5;66;03m# This uses GPT 4.1 nano, the incredibly cheap model\u001b[39;00m\n\u001b[32m 3\u001b[39m \u001b[38;5;66;03m# The APIs guide (guide 9) has exact instructions for using even cheaper or free alternatives to OpenAI\u001b[39;00m\n\u001b[32m 4\u001b[39m \u001b[38;5;66;03m# If you get a NameError, head to the guides folder (guide 6) to learn about NameErrors - always instantly fixable\u001b[39;00m\n\u001b[32m----> \u001b[39m\u001b[32m6\u001b[39m response = \u001b[43mopenai\u001b[49m\u001b[43m.\u001b[49m\u001b[43mchat\u001b[49m\u001b[43m.\u001b[49m\u001b[43mcompletions\u001b[49m\u001b[43m.\u001b[49m\u001b[43mcreate\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 7\u001b[39m \u001b[43m \u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m=\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mgoogle.gemma-3-12b-it\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[32m 8\u001b[39m \u001b[43m \u001b[49m\u001b[43mmessages\u001b[49m\u001b[43m=\u001b[49m\u001b[43mmessages\u001b[49m\n\u001b[32m 9\u001b[39m \u001b[43m)\u001b[49m\n\u001b[32m 11\u001b[39m \u001b[38;5;28mprint\u001b[39m(response.choices[\u001b[32m0\u001b[39m].message.content)\n", "\u001b[36mFile \u001b[39m\u001b[32mc:\\Users\\basil shahul\\projects\\agents\\.venv\\Lib\\site-packages\\openai\\_utils\\_utils.py:286\u001b[39m, in \u001b[36mrequired_args..inner..wrapper\u001b[39m\u001b[34m(*args, **kwargs)\u001b[39m\n\u001b[32m 284\u001b[39m msg = \u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mMissing required argument: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mquote(missing[\u001b[32m0\u001b[39m])\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m\"\u001b[39m\n\u001b[32m 285\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(msg)\n\u001b[32m--> \u001b[39m\u001b[32m286\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[43m*\u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", "\u001b[36mFile \u001b[39m\u001b[32mc:\\Users\\basil shahul\\projects\\agents\\.venv\\Lib\\site-packages\\openai\\resources\\chat\\completions\\completions.py:1147\u001b[39m, in \u001b[36mCompletions.create\u001b[39m\u001b[34m(self, messages, model, audio, frequency_penalty, function_call, functions, logit_bias, logprobs, max_completion_tokens, max_tokens, metadata, modalities, n, parallel_tool_calls, prediction, presence_penalty, prompt_cache_key, reasoning_effort, response_format, safety_identifier, seed, service_tier, stop, store, stream, stream_options, temperature, tool_choice, tools, top_logprobs, top_p, user, verbosity, web_search_options, extra_headers, extra_query, extra_body, timeout)\u001b[39m\n\u001b[32m 1101\u001b[39m \u001b[38;5;129m@required_args\u001b[39m([\u001b[33m\"\u001b[39m\u001b[33mmessages\u001b[39m\u001b[33m\"\u001b[39m, \u001b[33m\"\u001b[39m\u001b[33mmodel\u001b[39m\u001b[33m\"\u001b[39m], [\u001b[33m\"\u001b[39m\u001b[33mmessages\u001b[39m\u001b[33m\"\u001b[39m, \u001b[33m\"\u001b[39m\u001b[33mmodel\u001b[39m\u001b[33m\"\u001b[39m, \u001b[33m\"\u001b[39m\u001b[33mstream\u001b[39m\u001b[33m\"\u001b[39m])\n\u001b[32m 1102\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34mcreate\u001b[39m(\n\u001b[32m 1103\u001b[39m \u001b[38;5;28mself\u001b[39m,\n\u001b[32m (...)\u001b[39m\u001b[32m 1144\u001b[39m timeout: \u001b[38;5;28mfloat\u001b[39m | httpx.Timeout | \u001b[38;5;28;01mNone\u001b[39;00m | NotGiven = not_given,\n\u001b[32m 1145\u001b[39m ) -> ChatCompletion | Stream[ChatCompletionChunk]:\n\u001b[32m 1146\u001b[39m validate_response_format(response_format)\n\u001b[32m-> \u001b[39m\u001b[32m1147\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_post\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 1148\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43m/chat/completions\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[32m 1149\u001b[39m \u001b[43m \u001b[49m\u001b[43mbody\u001b[49m\u001b[43m=\u001b[49m\u001b[43mmaybe_transform\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 1150\u001b[39m \u001b[43m \u001b[49m\u001b[43m{\u001b[49m\n\u001b[32m 1151\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mmessages\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmessages\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1152\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mmodel\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1153\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43maudio\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43maudio\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1154\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mfrequency_penalty\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfrequency_penalty\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1155\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mfunction_call\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfunction_call\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1156\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mfunctions\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfunctions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1157\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mlogit_bias\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mlogit_bias\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1158\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mlogprobs\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mlogprobs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1159\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mmax_completion_tokens\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_completion_tokens\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1160\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mmax_tokens\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_tokens\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1161\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mmetadata\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmetadata\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1162\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mmodalities\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodalities\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1163\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mn\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mn\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1164\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mparallel_tool_calls\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mparallel_tool_calls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1165\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mprediction\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mprediction\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1166\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mpresence_penalty\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mpresence_penalty\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1167\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mprompt_cache_key\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mprompt_cache_key\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1168\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mreasoning_effort\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mreasoning_effort\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1169\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mresponse_format\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mresponse_format\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1170\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43msafety_identifier\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43msafety_identifier\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1171\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mseed\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mseed\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1172\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mservice_tier\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mservice_tier\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1173\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mstop\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1174\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mstore\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstore\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1175\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mstream\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1176\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mstream_options\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1177\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mtemperature\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtemperature\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1178\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mtool_choice\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtool_choice\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1179\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mtools\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtools\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1180\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mtop_logprobs\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtop_logprobs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1181\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mtop_p\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtop_p\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1182\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43muser\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43muser\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1183\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mverbosity\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mverbosity\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1184\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mweb_search_options\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mweb_search_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1185\u001b[39m \u001b[43m \u001b[49m\u001b[43m}\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1186\u001b[39m \u001b[43m \u001b[49m\u001b[43mcompletion_create_params\u001b[49m\u001b[43m.\u001b[49m\u001b[43mCompletionCreateParamsStreaming\u001b[49m\n\u001b[32m 1187\u001b[39m \u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\n\u001b[32m 1188\u001b[39m \u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mcompletion_create_params\u001b[49m\u001b[43m.\u001b[49m\u001b[43mCompletionCreateParamsNonStreaming\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1189\u001b[39m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1190\u001b[39m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[43m=\u001b[49m\u001b[43mmake_request_options\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 1191\u001b[39m \u001b[43m \u001b[49m\u001b[43mextra_headers\u001b[49m\u001b[43m=\u001b[49m\u001b[43mextra_headers\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mextra_query\u001b[49m\u001b[43m=\u001b[49m\u001b[43mextra_query\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mextra_body\u001b[49m\u001b[43m=\u001b[49m\u001b[43mextra_body\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[43m=\u001b[49m\u001b[43mtimeout\u001b[49m\n\u001b[32m 1192\u001b[39m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1193\u001b[39m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m=\u001b[49m\u001b[43mChatCompletion\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1194\u001b[39m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[43m=\u001b[49m\u001b[43mstream\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[32m 1195\u001b[39m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[43m=\u001b[49m\u001b[43mStream\u001b[49m\u001b[43m[\u001b[49m\u001b[43mChatCompletionChunk\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1196\u001b[39m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n", "\u001b[36mFile \u001b[39m\u001b[32mc:\\Users\\basil shahul\\projects\\agents\\.venv\\Lib\\site-packages\\openai\\_base_client.py:1259\u001b[39m, in \u001b[36mSyncAPIClient.post\u001b[39m\u001b[34m(self, path, cast_to, body, options, files, stream, stream_cls)\u001b[39m\n\u001b[32m 1245\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34mpost\u001b[39m(\n\u001b[32m 1246\u001b[39m \u001b[38;5;28mself\u001b[39m,\n\u001b[32m 1247\u001b[39m path: \u001b[38;5;28mstr\u001b[39m,\n\u001b[32m (...)\u001b[39m\u001b[32m 1254\u001b[39m stream_cls: \u001b[38;5;28mtype\u001b[39m[_StreamT] | \u001b[38;5;28;01mNone\u001b[39;00m = \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[32m 1255\u001b[39m ) -> ResponseT | _StreamT:\n\u001b[32m 1256\u001b[39m opts = FinalRequestOptions.construct(\n\u001b[32m 1257\u001b[39m method=\u001b[33m\"\u001b[39m\u001b[33mpost\u001b[39m\u001b[33m\"\u001b[39m, url=path, json_data=body, files=to_httpx_files(files), **options\n\u001b[32m 1258\u001b[39m )\n\u001b[32m-> \u001b[39m\u001b[32m1259\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m cast(ResponseT, \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mrequest\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mopts\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[43m=\u001b[49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[43m=\u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[43m)\u001b[49m)\n", "\u001b[36mFile \u001b[39m\u001b[32mc:\\Users\\basil shahul\\projects\\agents\\.venv\\Lib\\site-packages\\openai\\_base_client.py:1047\u001b[39m, in \u001b[36mSyncAPIClient.request\u001b[39m\u001b[34m(self, cast_to, options, stream, stream_cls)\u001b[39m\n\u001b[32m 1044\u001b[39m err.response.read()\n\u001b[32m 1046\u001b[39m log.debug(\u001b[33m\"\u001b[39m\u001b[33mRe-raising status error\u001b[39m\u001b[33m\"\u001b[39m)\n\u001b[32m-> \u001b[39m\u001b[32m1047\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;28mself\u001b[39m._make_status_error_from_response(err.response) \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[32m 1049\u001b[39m \u001b[38;5;28;01mbreak\u001b[39;00m\n\u001b[32m 1051\u001b[39m \u001b[38;5;28;01massert\u001b[39;00m response \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m, \u001b[33m\"\u001b[39m\u001b[33mcould not resolve response (should never happen)\u001b[39m\u001b[33m\"\u001b[39m\n", "\u001b[31mAuthenticationError\u001b[39m: Error code: 401 - {'error': {'message': 'Invalid API Key format: Must start with pre-defined prefix', 'type': 'permission_denied_error', 'param': None, 'code': 'access_denied'}}" ] } ], "source": [ "# And now call it! Any problems, head to the troubleshooting guide\n", "# This uses GPT 4.1 nano, the incredibly cheap model\n", "# The APIs guide (guide 9) has exact instructions for using even cheaper or free alternatives to OpenAI\n", "# If you get a NameError, head to the guides folder (guide 6) to learn about NameErrors - always instantly fixable\n", "\n", "response = openai.chat.completions.create(\n", " model=\"google.gemma-3-12b-it\",\n", " messages=messages\n", ")\n", "\n", "print(response.choices[0].message.content)\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# And now - let's ask for a question:\n", "\n", "question = \"Please propose a hard, challenging question to assess someone's IQ. Respond only with the question.\"\n", "messages = [{\"role\": \"user\", \"content\": question}]\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "A lighthouse keeper notices that the beam sweeps past his lighthouse every 60 minutes. He also observes that a nearby foghorn sounds every 75 minutes. He first notices both the beam and the horn sounding simultaneously. How long will it be, in minutes, until they next sound simultaneously?\n" ] } ], "source": [ "# ask it - this uses GPT 4.1 mini, still cheap but more powerful than nano\n", "\n", "response = openai.chat.completions.create(\n", " model=\"google.gemma-3-12b-it\",\n", " messages=messages\n", ")\n", "\n", "question = response.choices[0].message.content\n", "\n", "print(question)\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# form a new messages list\n", "messages = [{\"role\": \"user\", \"content\": question}]\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Let $B$ be the time in minutes when the lighthouse beam sweeps past the lighthouse.\n", "Let $H$ be the time in minutes when the foghorn sounds.\n", "The lighthouse beam sweeps past the lighthouse every 60 minutes, so it sweeps past at times $60n$ for $n=1, 2, 3, \\ldots$.\n", "The foghorn sounds every 75 minutes, so it sounds at times $75m$ for $m=1, 2, 3, \\ldots$.\n", "We are given that the lighthouse keeper first notices both the beam and the horn sounding simultaneously. Let $t=0$ be the time when both the beam and the horn sound simultaneously.\n", "We want to find the next time when both the beam and the horn sound simultaneously.\n", "This means we want to find the smallest positive value of $t$ such that $t=60n=75m$ for some integers $n$ and $m$.\n", "In other words, we want to find the least common multiple (LCM) of 60 and 75.\n", "\n", "To find the LCM of 60 and 75, we first find the prime factorization of each number:\n", "$60 = 2^2 \\cdot 3 \\cdot 5$\n", "$75 = 3 \\cdot 5^2$\n", "\n", "The LCM is the product of the highest powers of all the prime factors in the factorization of both numbers:\n", "LCM$(60, 75) = 2^2 \\cdot 3 \\cdot 5^2 = 4 \\cdot 3 \\cdot 25 = 12 \\cdot 25 = 300$\n", "\n", "Thus, the next time both the beam and the horn will sound simultaneously is 300 minutes.\n", "\n", "Final Answer: The final answer is $\\boxed{300}$\n", "A lighthouse keeper notices that the beam sweeps past his lighthouse every 60 minutes. He also observes that a nearby foghorn sounds every 75 minutes. He first notices both the beam and the horn sounding simultaneously. How long will it be, in minutes, until they next sound simultaneously?\n" ] } ], "source": [ "# Ask it again\n", "\n", "response = openai.chat.completions.create(\n", " model=\"google.gemma-3-12b-it\",\n", " messages=messages\n", ")\n", "\n", "answer = response.choices[0].message.content\n", "print(answer)\n", "print(question)\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/markdown": [ "Let $B$ be the time in minutes when the lighthouse beam sweeps past the lighthouse.\n", "Let $H$ be the time in minutes when the foghorn sounds.\n", "The lighthouse beam sweeps past the lighthouse every 60 minutes, so it sweeps past at times $60n$ for $n=1, 2, 3, \\ldots$.\n", "The foghorn sounds every 75 minutes, so it sounds at times $75m$ for $m=1, 2, 3, \\ldots$.\n", "We are given that the lighthouse keeper first notices both the beam and the horn sounding simultaneously. Let $t=0$ be the time when both the beam and the horn sound simultaneously.\n", "We want to find the next time when both the beam and the horn sound simultaneously.\n", "This means we want to find the smallest positive value of $t$ such that $t=60n=75m$ for some integers $n$ and $m$.\n", "In other words, we want to find the least common multiple (LCM) of 60 and 75.\n", "\n", "To find the LCM of 60 and 75, we first find the prime factorization of each number:\n", "$60 = 2^2 \\cdot 3 \\cdot 5$\n", "$75 = 3 \\cdot 5^2$\n", "\n", "The LCM is the product of the highest powers of all the prime factors in the factorization of both numbers:\n", "LCM$(60, 75) = 2^2 \\cdot 3 \\cdot 5^2 = 4 \\cdot 3 \\cdot 25 = 12 \\cdot 25 = 300$\n", "\n", "Thus, the next time both the beam and the horn will sound simultaneously is 300 minutes.\n", "\n", "Final Answer: The final answer is $\\boxed{300}$" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "A lighthouse keeper notices that the beam sweeps past his lighthouse every 60 minutes. He also observes that a nearby foghorn sounds every 75 minutes. He first notices both the beam and the horn sounding simultaneously. How long will it be, in minutes, until they next sound simultaneously?\n" ] } ], "source": [ "from IPython.display import Markdown, display\n", "\n", "display(Markdown(answer))\n", "print(question)\n", "\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Congratulations!\n", "\n", "That was a small, simple step in the direction of Agentic AI, with your new environment!\n", "\n", "Next time things get more interesting..." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", " \n", " \n", " \n", " \n", "
\n", " \n", " \n", "

Exercise

\n", " Now try this commercial application:
\n", " First ask the LLM to pick a business area that might be worth exploring for an Agentic AI opportunity.
\n", " Then ask the LLM to present a pain-point in that industry - something challenging that might be ripe for an Agentic solution.
\n", " Finally have 3 third LLM call propose the Agentic AI solution.
\n", " We will cover this at up-coming labs, so don't worry if you're unsure.. just give it a try!\n", " \n", "
" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Okay, this is *excellent*. You've identified a real pain point and have mapped out a truly compelling solution. CreatorAI has a lot of potential, and your agentic AI approach is spot-on for tackling such a multifaceted problem. Let's break down your points and then I'll answer your refining questions at the end.\n", "\n", "**Strong Points of Your Proposal:**\n", "\n", "* **Well-Defined Target Audience:** Focusing on mid-tier creators is brilliant. It's a large, underserved market willing to pay for a solution that significantly eases their workload. Going after mega-influencers is a much higher-stakes, more competitive battle.\n", "* **Holistic Approach:** You’re not just selling content creation; you’re selling a complete content lifecycle management solution. That's the key differentiator.\n", "* **Agentic AI is the Right Choice:** You've correctly recognized that a suite of specialized agents is necessary for the complexity involved. The division of labor you’ve outlined – Strategy, Creation, Performance, Feedback – is logical and effective.\n", "* **Proactive vs. Reactive Emphasized:** This is crucial. The promise of proactive assistance – anticipating needs and suggesting actions – is far more valuable than just a content-generating tool.\n", "* **Realistic Challenges Acknowledged:** You've identified the key hurdles – data privacy, AI accuracy, human oversight, and development costs. Acknowledging these from the start is responsible.\n", "\n", "**Areas for Further Consideration/Refinement (without changing the core concept – this is all about polishing):**\n", "\n", "* **Data Integration - The Backbone:** The biggest logistical challenge (and potential competitive moat) will be the ease and reliability of connecting to various content platforms (YouTube, WordPress, Substack, Spotify, etc.). This needs to be incredibly smooth and secure. Think about API integrations, potential partnership deals with these platforms, and user authentication – this is the *plumbing* of your system.\n", "* **Brand Voice & Style:** While the agents can generate content, creators have a distinct brand voice and style. How will CreatorAI learn and maintain that voice? Will users upload samples of their work for \"voice training\"? Will there be controls for tone (e.g., humorous, formal, informative)? A strong voice model is vital.\n", "* **Creative Block Breakthrough:** Mid-tier creators sometimes have periods of complete creative block. A \"jumpstart\" agent, perhaps integrated with the Strategy Agent, could be specifically designed to break through that – providing unexpected prompts, mixing formats, and suggesting entirely new content directions.\n", "* **Community & Support:** Consider integrating a community forum where creators can share tips, ask questions, and provide feedback on CreatorAI. Strong community builds stickiness and provides invaluable qualitative data for improving the platform.\n", "* **Monetization Agent Depth:** You mention monetization. Take this a step further. Could the Monetization Agent research affiliate programs *specifically* relevant to the content, negotiate sponsorships (potentially!), or even help set up and manage a digital product store?\n", "* **Transparency & Control:** Creators will want to understand *why* the agents are recommending certain actions. A \"Transparency Dashboard\" that explains the rationale behind the Strategy Agent’s decisions could build trust and foster a collaborative relationship with the AI.\n", "* **Workflow Customization:** Give users the ability to customize the agents' roles and responsibilities. Some creators might want more agent involvement in content creation, while others might prefer a more advisory role.\n", "\n", "**Now, to answer your refining questions:**\n", "\n", "* **What specific aspects of this idea are most interesting to you?** Primarily, the *agentic AI orchestration* and the focus on *proactive, data-driven strategy*. Many AI tools are reactive; CreatorAI's ability to anticipate and plan is a huge differentiator. I also find the \"Feedback Loop Agent\" particularly compelling – it's the key to long-term success and adaptability. The entire notion of a 'virtual content assistant' who proactively helps navigate monetization is brilliant.\n", "* **Are there any similar products on the market you’re already aware of, and where do they fall short?** Yes, several. Here's a quick breakdown:\n", " * **Jasper/Copy.ai:** Content generation, but lack the strategic and optimization components. They're tools *within* a process, not the entire process.\n", " * **Semrush/Ahrefs:** SEO and keyword research, but don’t generate content or integrate with content platforms.\n", " * **Simplified.co:** Attempts to combine some of these features, but its agentic capabilities are very limited, and often feels disjointed.\n", " * **Buffer/Hootsuite:** Scheduling and some social media analytics, but not focused on content creation, SEO, or broader monetization strategies.\n", " * **Key Shortcomings Across These:** *Lack of proactivity*, *poor integration*, *no truly holistic strategy*, and *limited learning/adaptation*. They are tools, not a partner.\n", "* **What are your thoughts on the potential pricing model for such a platform?** Tiered subscription is almost certainly the way to go. Here's a possible structure:\n", "\n", " * **\"Spark\" (Free Tier):** Limited features, perhaps access to one agent (e.g., Basic Keyword Research) and a limited number of content generations per month. A lead-generation tool.\n", " * **\"Growth\" ($49 - $99/month):** Full access to all agents, unlimited content generation, basic analytics reporting, integration with 1-2 content platforms. Suitable for bloggers and podcasters just getting serious.\n", " * **\"Pro\" ($149 - $299/month):** Everything in \"Growth\" plus advanced analytics, integration with multiple platforms, personalized onboarding/training, priority support, and possibly some basic monetization consulting. Ideal for established mid-tier creators.\n", " * **\"Agency\" (Custom Pricing):** For creators with teams, more complex integration needs, or requiring advanced strategy consulting.\n", "\n", " **Considerations:**\n", " * **Usage-Based add-ons:** Offer the ability to purchase extra “content generations” if users exceed their monthly limit.\n", " * **\"Monetization Booster\" Add-on:** A higher-priced tier focusing specifically on monetization strategies and potentially offering a commission-based revenue share model.\n", "\n", "\n", "\n", "Your CreatorAI concept is exceptionally strong. With careful execution and attention to detail—particularly around data integration and brand voice—you have the potential to disrupt the creator economy and empower a vast segment of content creators. Keep building!\n" ] } ], "source": [ "# First create the messages:\n", "\n", "messages = [{\"role\": \"user\", \"content\": \"pick a buisness idea that might be worth exploring for an agentic ai opporutnity\"}]\n", "\n", "# Then make the first call:\n", "\n", "response = openai.chat.completions.create(\n", " model=\"google.gemma-3-12b-it\",\n", " messages=messages\n", ")\n", "\n", "# Then read the business idea:\n", "\n", "business_idea = response.choices[0].message.content\n", "\n", "messages = [{\"role\": \"user\", \"content\": \"what is the pain point in this industry?\" + business_idea}]\n", "\n", "# And repeat! In the next message, include the business idea within the message\n", "\n", "response2 = openai.chat.completions.create(\n", " model=\"google.gemma-3-12b-it\",\n", " messages=messages\n", ")\n", "\n", "pain_point = response.choices[0].message.content\n", "\n", "messages = [{\"role\": \"user\", \"content\": \"Give a solution for this pain point\" + pain_point}]\n", "\n", "\n", "response3 = openai.chat.completions.create(\n", " model=\"google.gemma-3-12b-it\",\n", " messages=messages\n", ")\n", "\n", "print(response3.choices[0].message.content)\n", "\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [] } ], "metadata": { "kernelspec": { "display_name": "agents", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.12.6" } }, "nbformat": 4, "nbformat_minor": 2 }